AI Paper Atlas

Research map / Graph learning / Graph self-supervised learning

SFGA: Similarity-Constrained Fusion Learning for Unsupervised Anomaly Detection in Multiplex Graphs

Huiliang Zhai, Xiangyi Teng, Jing Liu

AAAI 2026 · Graph learning › Graph self-supervised learning · approach: Graph anomaly detection · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add inter-relation attention (ATT) (ablation)SFGA · YelpChiAUROC: 59.63 -> 70.06Improved
add inter-relation attention (ATT) (ablation)SFGA · YelpChiAUPRC: 19.83 -> 24.68Improved
add similarity constraint (SC) (ablation)SFGA · YelpChiAUROC: 67.99 -> 70.06Improved
add similarity constraint (SC) (ablation)SFGA · AmazonAUPRC: 13.17 -> 16.39Improved
add hierarchical anomaly detector (HD) (ablation)SFGA · YelpChiAUROC: 67.82 -> 70.06Improved
add hierarchical anomaly detector (HD) (ablation)SFGA · AmazonAUPRC: 15.79 -> 16.39No clear effect
combine ATT, SC and HD (ablation)SFGA · YelpChiAUROC: 51.44 -> 70.06Improved
vary alpha (loss weight) from 0 to 1 (ablation)SFGA · AmazonAUROC/AUPRCMixed
vary beta (score weight) from 0 to 1 (ablation)SFGA · AmazonAUROC/AUPRCMixed
multiplex SFGA vs homogeneous GAD baselinesSFGA · FreebaseAUROC: 84.89 -> 92.98Improved
multiplex SFGA vs TAMSFGA · AmazonAUPRC: 34.19 -> 16.39Hurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy